Training complete

README.md

@@ -15,16 +15,16 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/codebert-base](https://huggingface.co/microsoft/codebert-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 18.2530
-- eval_rouge1: 0.0557
-- eval_rouge2: 0.0041
-- eval_rougeL: 0.0397
-- eval_bleu: 0.8313
-- eval_meteor: 0.0884
-- eval_codebleu: 0.2407
-- eval_runtime: 150.2026
-- eval_samples_per_second: 0.067
-- eval_steps_per_second: 0.013
+- eval_loss: 17.9546
+- eval_rouge1: 0.0741
+- eval_rouge2: 0.0047
+- eval_rougeL: 0.0528
+- eval_bleu: 1.0975
+- eval_meteor: 0.0974
+- eval_codebleu: {'codebleu': 0.2174788437391285, 'ngram_match_score': 0.0007172304133318851, 'weighted_ngram_match_score': 0.0015773932015006452, 'syntax_match_score': 0.07692307692307693, 'dataflow_match_score': 0.7906976744186046}
+- eval_runtime: 40.1888
+- eval_samples_per_second: 0.249
+- eval_steps_per_second: 0.025
 - step: 0
 
 ## Model description
@@ -45,8 +45,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 32
+- eval_batch_size: 64
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear

config.json

@@ -12,6 +12,7 @@
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
+  "is_decoder": true,
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
   "model_type": "roberta",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:916dc519bdf65a462f90cb40768d07e186ba8a812a9687855fb967bd09f1873d
+oid sha256:221ef71ce2f5de5811df7c6ef40413e590833be4b780f714c6f9f41e4b52c141
 size 498813948

runs/Jul26_17-48-33_30aead859e7a/events.out.tfevents.1722016153.30aead859e7a.53813.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:920c1d3e92e4b7649b41a6e46a96942133b6009fe833cb4eb531d212d1917e44
+size 530

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 128,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 128
-    },
-    "direction": "Left",
-    "pad_to_multiple_of": null,
-    "pad_id": 2,
-    "pad_type_id": 0,
-    "pad_token": "</s>"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c63e64576549df8ac6dd7cfd5063324309b17aa0470e25f17ff207a0c85ea682
+oid sha256:aab5322319da1eef8a45a74e25425c600d2eccd011bc4dd74b8d87c79f119789
 size 5304